hashbulla
UserA human-gated, 7-phase agentic deep-research skill for Claude Code. Fans out across the open web (Tavily), GitHub, academic open-graphs (OpenAlex/arXiv/Semantic Scholar), and live library docs — then grades every source on the NATO Admiralty A–F scale, runs deterministic quality gates, and emits four cited artifacts.
Categories
Indexed Skills (2)
suggest-tooling
Propose work-relevant Claude Code skills, plugins, and MCP servers from a finished deep-research run; relevance-ranked and trust-tier-graded; never auto-installed. Load when the user says "/suggest-tooling <run-dir>", "propose tools for my research run", "what skills match this research", "suggère des outils pour ce run", or when deep-research delegates with --suggest-tooling. Do NOT activate for: installing or registering tools; single-tool lookup ("what does X do"); non-Claude-ecosystem tooling (npm packages, Python libs); running a fresh research run (use deep-research for that).
deep-research
Agentic multi-source deep research via Tavily MCP, calibrated to Perplexity Deep Research (100+ sources on exhaustive runs). Load when the user wants a planned, source-graded research report — /deep-research, "deep research on X", "recherche approfondie sur X", "analyse multi-sources", "comparative analysis with sources". Do NOT load for single-fact lookups, known-URL extractions, library doc lookups (use tavily_skill), or quick research with no graded artifacts (use /research or the plugin-namespaced deep-research sibling — this skill is the 7-phase pipeline emitting four NATO-graded, script-verified artifacts; it runs autonomously and only pauses to ask a clarifying question when the query is genuinely ambiguous).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.